Tribunal TRT18: Certidão Eletrônica de Ações Trabalhistas (CEAT)

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate readOnly=false, idempotent=true, but no high-risk mutations are implied. The description adds significant behavioral context: it explains the authentication flow, the two ways to authenticate (config header vs token), and the consequence of each (permanent vs session). It also clarifies that calling with no args yields a link. This goes well beyond annotations, covering side effects and setup requirements.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense but not overly long. It front-loads the core purpose ('log in in the browser, copy the access token') and then explains the two usage modes. Each sentence provides necessary information—no filler. However, it could be slightly reorganized to separate instructions from context, but it remains effective and readable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple input schema (one optional param, no output schema), the description is complete. It covers all usage scenarios: obtaining the link, passing a token, and the recommended permanent config method. It also addresses potential user questions (expiration, persistence) implicitly. There are no obvious gaps for the agent to act effectively.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has only one optional parameter with no description (schema coverage 0%). The description fully compensates by explaining the meaning of 'token' (a JWT) and how it is used (passed for session login, omitted to get a link). It also clarifies the relationship between this parameter and the alternative permanent configuration. This is excellent semantic coverage for a single parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: to authenticate with MCP.AI for IDE agents. It specifies a concrete action (authenticate) and resource (MCP.AI), and distinguishes itself from siblings like 'connect' and 'report_bug' by focusing solely on authentication. It also explains the two modes (permanent config vs session token), which directly addresses the 'what' and 'how'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear instructions for both use cases: adding a token to the server config for permanent access, or passing a token for a session-only login. It also explains that calling with no arguments returns a login link. It doesn't explicitly compare to sibling tools, but this is acceptable because the tool's purpose is inherently distinct. The guidance is practical and actionable.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly and idempotent hints, lowering the bar for description. The description adds valuable conditional logic about output variations, making the tool's behavior transparent without redundancy.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is brief (two sentences) and front-loaded with the core purpose. Every sentence adds useful detail about output conditions, with no filler or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a connection status tool with no parameters and no output schema, the description fully explains what the tool returns and under what conditions. It covers all essential information without over-specifying.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There are no parameters, so the baseline is 4. The description does not need to add parameter meaning since none exist. It could not add further detail, so it meets the baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: 'Returns connection status and URLs.' It is specific about the resource and action, and distinguishes from sibling tools by focusing on status checking without mentioning other operations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides conditional behaviors ('When all providers are connected... returns authenticated:true' and 'When credentials are missing... returns connect_url'), giving context on when to expect different outcomes. However, it does not explicitly mention alternative tools or exclusion scenarios, though that may be unnecessary given the tool's focused purpose.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description goes well beyond the minimal annotations (readOnlyHint:false, etc.) by explaining that invoke runs tools even if not installed, that authentication/payment link flows exist, and that writes require admin privileges. It also discloses the distinction between installed_in_toolkit vs installed_in_workspace. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single dense paragraph with no structural breaks or bullets, making it hard to parse quickly. It contains a lot of information, but it is not compactly organized. Some sentences are long and wrap multiple ideas, reducing clarity. It could be simplified into a flow description and action list, but it does not waste words on fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (23 parameters, multiple sub-actions, no output schema), the description covers the main workflow and behavioral outcomes well, but it lacks details on return formats, pagination for search, error handling, or what each action returns concretely. It is adequate for basic usage but leaves uncertainty about output structures.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With zero schema description coverage, the description compensates by explaining the most important parameter 'action' and its enumerations, and outlines how parameters like tool_id, arguments, and prompt_* are used in the flow. However, it leaves several parameters (e.g., limit, message, immediate, conversation, cancel_reason) without explicit explanation, though their purpose can be inferred from context. It adds substantial value but isn't exhaustive.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's role as the official mcp.ai marketplace and catalog of MCPs/tools, with a detailed core flow (search→describe→invoke). It distinguishes itself from siblings by covering a broad range of actions (search, install, prompt library) and explicitly mentions how it relates to the toolkit and other tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit guidance on when to use invoke vs install, when writes require owner/admin, and how to handle credential/payment cases. It also explains the prompt library and its actions, making it clear when and how to use each sub-action. Alternatives are addressed (e.g., 'prefer invoke for a single/occasional use').

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations supply non-destructive and idempotent hints, so the description does not need to duplicate them. The description adds that the conversation is for reproduction; however, it leaves out side effects, deduplication, rate limits, or user-facing outcomes. This is adequate but not richly transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences total, no filler. The first sentence states the purpose immediately and the second provides actionable reproduction guidance. It is tightly structured and quick to scan.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple enough that the description nearly suffices for the main use case. But the unexplained context parameter, conversation-vs-array mismatch, and lack of any return/confirmation behavior mean an agent would still have to guess when invoking beyond the required text message.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It only explains-conversation parameter, and even then calls it an 'array' while the schema declares type string. The required message and the optional context parameters are left unexplained, and the description makes conversation seem more important than the schema's optional/default behavior indicates.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with 'Report a bug, missing feature, or send feedback,' a specific verb and clear set of resources. None of the sibling tools are reporting tools, so this cleanly distinguishes the function from the rest.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The valid use cases are explicit: bug, missing feature, and generic feedback. There is no 'when not to use' or explicit alternative named, but the sibling list has no competing tool, so the context is still clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations (readOnly, idempotent, non-destructive) already disclose the behavioral traits. The description adds no extra details but is fully consistent with these annotations, so no contradiction exists.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, clear sentence with no unnecessary words. It gets straight to the point without any fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple version-check tool, the description fully conveys what the tool does and implies what the output will be (the versions). There is no missing context that would confuse a user or AI agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There are no parameters to describe; the schema confirms an empty object. The description does not need to explain parameters, making this trivially complete.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The verb 'Show' and resource 'current MCP platform and adapter versions' clearly specifies the tool's function. It is distinct from sibling tools like 'authenticate' or 'connect', which have different purposes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

While no explicit 'when to use' is stated, the tool's simplicity makes its usage obvious—whenever version information is needed. It does not mention alternatives, but given the trivial nature, this is sufficient.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and idempotentHint=true, but the description adds useful specifics about what data is returned, such as 'installed MCPs' and 'how many catalog tools each exposes'. While it doesn't discuss side effects or edge cases, the description aligns with and enriches the annotation context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, focused sentence front-loads the action and lists all relevant return fields without any fluff or repetition. Every word earns its place, making it highly efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and no parameters, the description carries the full burden of informing the agent about the tool's return. It covers all key aspects (installed MCPs, status, accounts, counts) and is sufficiently complete for an agent to decide when to call this tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the baseline is 4 per rubric. The description adds value by detailing the output structure, which is the only schema-adjacent information available, even though it doesn't discuss parameter semantics directly.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb 'Returns' and clearly defines the resource: 'current toolkit state'. It then enumerates the exact data returned (installed MCPs, connection status, accounts, catalog tool counts), making it distinct from all sibling tools like connect or show_version.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage context is implied by the description: it returns state, so it is likely used to inspect before acting. However, there is no explicit statement about when to prefer this tool over alternatives or when not to use it, leaving the guidance at an implied level.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the readOnly/idempotent/non-destructive annotations, the description discloses the prepaid per-query pricing, the lack of platform credentials, the official data source, and the LGPD controller responsibility. It does not mention failure modes or output shape, but annotations already cover the safety profile.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three dense sentences front-load the purpose and then add payment, credential, and legal context without repetition or filler. Every sentence contributes new, useful information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only query with rich annotations, the description is mostly complete, covering purpose, cost, credentials, and legal responsibility. However, with no output schema and no parameter description, it falls short of explaining what the CEAT response contains or how the parameters should be combined (CPF vs CNPJ, required requester data).

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the description adds no parameter-level guidance. The Portuguese field names (cpf, cnpj, cpf_requerente, nome_requerente) give some hints, but the distinction between the target subject and the 'requerente', and which fields are optional, is left to inference.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('consulta') and the specific resource ('Certidão Eletrônica de Ações Trabalhistas (CEAT)' from 'Tribunal TRT18' at an official source). This is specific enough to distinguish it from the unrelated sibling tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides practical context: no platform credentials are needed, the call is paid with prepaid credit, and the data is official/non-confidential. It does not explicitly name alternatives or exclusions, but the use case is clearly implied and the siblings are not competing tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.